© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 141266
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =nil
    -0.27
    ï¼Įé»ĺ认
    -0.27
    ↵			↵
    -0.27
    æī¶
    -0.26
    alian
    -0.26
    è¿ĺåı¯
    -0.24
    MING
    -0.24
    &id
    -0.24
    aten
    -0.24
    ↵				↵
    -0.24
    POSITIVE LOGITS
     emit
    0.25
     landscapes
    0.25
    ç´ł
    0.24
    XMLElement
    0.24
     resignation
    0.24
    ç½²
    0.24
    æī¿åĬŀ
    0.23
    纱
    0.23
    .setStyle
    0.23
    æĴŃ
    0.23
    Activations Density 15.776%

    No Known Activations

    This feature has no known activations.